Application of Neural Network Predictive Control Methods to Solve the Shipping Container Sway Control Problem in Quay Cranes

Abstract

Smart control systems are mostly applied in industry to control the movements of heavy machinery while optimizing overall operational efficiency. Major shipping companies use large quay cranes to load and unload containers from ships and still rely on the experience of on-site operators to perform transportation control procedures using joysticks and visual contact methods. This paper presents the research results of an EU-funded project for the Klaipeda container terminal to develop a novel container transportation security and cargo safety assurance method and system. It was concluded that many risks arise during the container handling procedures performed by the quay cranes and operators. To minimize these risks, the authors proposed controlling the sway of the spreader using a model predictive control method which applies a multi-layer perceptron (MLP) neural network (NN). The paper analyzes current neural network architectures and case studies and provides the engineering community with a unique case study which applies real operation statistical data. Several key training algorithms were tested, and the initial results suggest that the Levenberg-Marquardt (LM) algorithm and variable learning rate backpropagation perform better than methods which use the multi-layer perceptron neural network structure.

Remote sensing based forest cover classification using machine learning

“…Artificial Neural Networks (ANNs) have proven effective across diverse applications in remote sensing, such as land cover classification 8 , object detection 11 , vegetation and crops monitoring 4 , and terrain analysis 8 . Artificial Neural Networks find applications in various domains such as image processing and character recognition 31 , classification 32 , forecasting, enhancement 33 , analysis 34 , estimation, and prediction 35 . Their adaptability renders them suitable for a broad spectrum of tasks within the field.…”

Detecting Shipping Container Impacts with Vertical Cell Guides inside Container Ships during Handling Operations

“…Regarding the control operations, Predictive Model Controllers (MPC) are widely used to control heavy machinery and they tend to perform quite well [ 36 ]. The application of AI methods in these MPC control systems [ 1 , 37 , 38 ] tends to result in more efficient performance compared to regular methods and on-site human operators. However, these kinds of systems are mainly developed to be used as supporting tools in the form of decision support programs that highlight the optimum speed of transportation and the best movement patterns for containers and other means of transport within the terminal.…”

“…Port operators and shipping companies constantly face several serious problems related to shipping container handling in the port environment while transporting shipping containers and performing handling operations with port infrastructure [ 1 ]. From an engineering perspective, the most common handling mistakes occur during the transportation of shipping containers from container ships [ 2 ].…”

An improved approach for model predictive control in 3-D overhead crane systems

“…As a result, more advanced control strategies have been proposed, primarily based on nonlinear dynamic models created for overhead cranes, including the application of adaptive control [8] and model-free control techniques based on fuzzy logic [9][10][11]. Other methods, including the neural network predictive control method [12] and time-optimal control [13], have been used successfully to create anti-sway trolley paths based on studying the crane system's natural frequency.…”